Energy-efficient location tracking with smartphones for IoT

Location tracking is one of the most important applications for Internet of Things (IoT). Meanwhile, location sensing applications have become increasingly popular on smart-phones, since many, if not all, smartphones are equipped with a powerful sensor set, which includes GPS, WiFi, accelerometer, orientation, etc. Unfortunately, as the core enabler of most location sensing applications, GPS incurs an unacceptable energy cost that can cause complete battery drain within a few hours. In this paper we introduce SensTrack, a location tracking service which leverages sensor hints on the smartphone to reduce the usage of GPS. SensTrack selectively executes a GPS sampling by utilizing the information from accelerometer and orientation sensor, and switches to alternate location sensing method based on WiFi when users go indoors. A machine learning technique, Gaussian Process Regression, is then employed to reconstruct the track from recorded location samples. Evaluation on traces from real users demonstrates that SensTrack can significantly reduce the usage of GPS and still achieve good tracking accuracy.